{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2109.05093","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","created":"2021-09-10","cited_by_count":411},{"id":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349},{"id":"1811.03115","title":"Blockwise Parallel Decoding for Deep Autoregressive Models","created":"2018-11-07","cited_by_count":323},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"1704.07138","title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","created":"2017-04-24","cited_by_count":237},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"2312.12456","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","created":"2023-12-16","cited_by_count":217},{"id":"1903.06059","title":"Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement","created":"2019-03-14","cited_by_count":211},{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"2305.13971","title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","created":"2023-05-23","cited_by_count":197},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196},{"id":"1804.06609","title":"Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation","created":"2018-04-18","cited_by_count":182},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143},{"id":"1606.02960","title":"Sequence-to-Sequence Learning as Beam-Search Optimization","created":"2016-06-09","cited_by_count":127},{"id":"2402.04253","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","created":"2024-02-06","cited_by_count":124},{"id":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123},{"id":"2010.02650","title":"If beam search is the answer, what was the question?","created":"2020-10-06","cited_by_count":116},{"id":"1908.10090","title":"On NMT Search Errors and Model Errors: Cat Got Your Tongue?","created":"2019-08-27","cited_by_count":114},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95},{"id":"2303.04132","title":"Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction","created":"2023-03-07","cited_by_count":89},{"id":"2307.02628","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","created":"2023-07-05","cited_by_count":89},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79},{"id":"2311.04254","title":"Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation","created":"2023-11-07","cited_by_count":74},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72},{"id":"2402.16352","title":"MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs","created":"2024-02-26","cited_by_count":72},{"id":"2302.00763","title":"Collaborating with language models for embodied reasoning","created":"2023-02-01","cited_by_count":61},{"id":"2402.01981","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","created":"2024-02-03","cited_by_count":59},{"id":"2312.12343","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","created":"2023-12-19","cited_by_count":58},{"id":"2112.08340","title":"GenIE: Generative Information Extraction","created":"2021-12-15","cited_by_count":53},{"id":"2305.11499","title":"RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought","created":"2023-05-19","cited_by_count":47},{"id":"1704.03899","title":"Deep Reinforcement Learning-based Image Captioning with Embedding Reward","created":"2017-04-12","cited_by_count":40},{"id":"2305.15041","title":"Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science","created":"2023-05-24","cited_by_count":37},{"id":"2109.13582","title":"PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding","created":"2021-09-28","cited_by_count":33},{"id":"2312.01797","title":"LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics","created":"2023-12-04","cited_by_count":26},{"id":"2306.07932","title":"Human-in-the-Loop through Chain-of-Thought","created":"2023-06-10","cited_by_count":20},{"id":"2307.03749","title":"On the Efficacy of Sampling Adapters","created":"2023-07-07","cited_by_count":17},{"id":"2312.01059","title":"Swarm-GPT: Combining Large Language Models with Safe Motion Planning for Robot Choreography Design","created":"2023-12-02","cited_by_count":15},{"id":"1902.06022","title":"A Fully Differentiable Beam Search Decoder","created":"2019-02-16","cited_by_count":14},{"id":"2109.11034","title":"Conditional Poisson Stochastic Beam Search","created":"2021-09-22","cited_by_count":11},{"id":"2210.07228","title":"Language Model Decoding as Likelihood-Utility Alignment","created":"2022-10-13","cited_by_count":5}],"next_cursor":null}